qa-explain-behavior
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process a project's codebase to explain its behavior. This represents an attack surface where malicious comments or data within the codebase could attempt to influence the agent's output. However, the skill includes explicit instructions to avoid implementation details, framework terminology, and code generation, which serves as a natural constraint against many common injection goals. The risk is inherent to the skill's primary function and is considered low.
- [DATA_EXPOSURE]: While the skill directs the agent to investigate configuration and service layers, it explicitly instructs the agent to ignore database schemas, credentials, variable names, and implementation internals. This scoping reduces the likelihood of accidental exposure of sensitive environment variables or secrets during the explanation process.
- [COMMAND_EXECUTION]: The skill does not contain any instructions to execute shell commands, system calls, or subprocesses. It is strictly a text-processing and explanation tool.
- [EXTERNAL_DOWNLOADS]: The skill does not reference any external URLs, remote scripts, or third-party package registries. All logic is contained within the provided markdown and reference files.
Audit Metadata